INVESTIGADORES
SOSA ESCUDERO Walter Esteban
artículos
Título:
Level-based estimation of dynamic panel models
Autor/es:
GABRIEL MONTES ROJAS; SOSA ESCUDERO, WALTER; FEDERICO ZINCENKO
Revista:
Journal of Econometric Methods
Editorial:
De Gruyter
Referencias:
Año: 2019
ISSN:
2156-6674
Resumen:
This paper develops an alternative estimator for linear dynamic panel datamodels based on parameterizing the covariances between covariates and unobserved time-invariant effects. A GMM framework is used to derive an optimalestimator based on moment conditions in levels, with no efficiency loss compared to the classic alternatives like Arellano and Bond (1991) and Ahn andSchmidt (1995, 1997). Still, we show analytically and by Monte Carlo simulations that the new procedure leads to efficiency improvements for certaindata generating processes. The framework also leads to a very simple test forunobserved effects.
